{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQKC6Q2K3M6EFEPSVRY4BCBE6A","short_pith_number":"pith:GQKC6Q2K","schema_version":"1.0","canonical_sha256":"34142f434adb3c4291f2ac71c08824f015c69fdfbb9bfea67dfca6b7ca43aa25","source":{"kind":"arxiv","id":"2410.12773","version":1},"attestation_state":"computed","paper":{"title":"Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jinhan Li, Ye Yuan, Yifeng Zhu, Yuke Zhu, Yuqi Xie, Zhenyu Jiang","submitted_at":"2024-10-16T17:48:50Z","abstract_excerpt":"Humanoid robots, with their human-like embodiment, have the potential to integrate seamlessly into human environments. Critical to their coexistence and cooperation with humans is the ability to understand natural language communications and exhibit human-like behaviors. This work focuses on generating diverse whole-body motions for humanoid robots from language descriptions. We leverage human motion priors from extensive human motion datasets to initialize humanoid motions and employ the commonsense reasoning capabilities of Vision Language Models (VLMs) to edit and refine these motions. Our "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.12773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-16T17:48:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c79e251a504e38402d97b97d5108ecdd7aee30eb6ccce179c2b7a8f509cdffa","abstract_canon_sha256":"9846a4d31d7de87baf5bff8eeaec05443f8f39943bf966e317c73d932371475a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:33.732530Z","signature_b64":"VccfiSe8Pa3RSwrEt2FMZdrV+O2a8MVqyxFcW1ejkfswg26LwhhlU3zohsskZtiOf8xTdSLKOXRT3ZN8arsIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34142f434adb3c4291f2ac71c08824f015c69fdfbb9bfea67dfca6b7ca43aa25","last_reissued_at":"2026-07-05T09:21:33.732036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:33.732036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jinhan Li, Ye Yuan, Yifeng Zhu, Yuke Zhu, Yuqi Xie, Zhenyu Jiang","submitted_at":"2024-10-16T17:48:50Z","abstract_excerpt":"Humanoid robots, with their human-like embodiment, have the potential to integrate seamlessly into human environments. Critical to their coexistence and cooperation with humans is the ability to understand natural language communications and exhibit human-like behaviors. This work focuses on generating diverse whole-body motions for humanoid robots from language descriptions. We leverage human motion priors from extensive human motion datasets to initialize humanoid motions and employ the commonsense reasoning capabilities of Vision Language Models (VLMs) to edit and refine these motions. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12773","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.12773/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.12773","created_at":"2026-07-05T09:21:33.732094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12773v1","created_at":"2026-07-05T09:21:33.732094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12773","created_at":"2026-07-05T09:21:33.732094+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQKC6Q2K3M6E","created_at":"2026-07-05T09:21:33.732094+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQKC6Q2K3M6EFEPS","created_at":"2026-07-05T09:21:33.732094+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQKC6Q2K","created_at":"2026-07-05T09:21:33.732094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07765","citing_title":"Toward Seamless Physical Human-Humanoid Interaction: Insights from Control, Intent, and Modeling with a Vision for What Comes Next","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17807","citing_title":"Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A","json":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A.json","graph_json":"https://pith.science/api/pith-number/GQKC6Q2K3M6EFEPSVRY4BCBE6A/graph.json","events_json":"https://pith.science/api/pith-number/GQKC6Q2K3M6EFEPSVRY4BCBE6A/events.json","paper":"https://pith.science/paper/GQKC6Q2K"},"agent_actions":{"view_html":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A","download_json":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A.json","view_paper":"https://pith.science/paper/GQKC6Q2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12773&json=true","fetch_graph":"https://pith.science/api/pith-number/GQKC6Q2K3M6EFEPSVRY4BCBE6A/graph.json","fetch_events":"https://pith.science/api/pith-number/GQKC6Q2K3M6EFEPSVRY4BCBE6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A/action/storage_attestation","attest_author":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A/action/author_attestation","sign_citation":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A/action/citation_signature","submit_replication":"https://pith.science/pith/GQKC6Q2K3M6EFEPSVRY4BCBE6A/action/replication_record"}},"created_at":"2026-07-05T09:21:33.732094+00:00","updated_at":"2026-07-05T09:21:33.732094+00:00"}